Interpreting LLMs as Credit Risk Classifiers: Do Their Feature Explanations Align with Classical ML?

Large Language Models (LLMs) are increasingly explored as flexible alternatives to classical machine learning models for classification tasks through zero-shot prompting. However, their suitability for structured tabular data remains underexplored, especially in high-stakes financial applications such as financial risk assessment. This study conducts a systematic comparison between zero-shot LLM-based classifiers and LightGBM, a state-of-the-art gradient-boosting model, on a real-world loan default prediction task. We evaluate their predictive performance, analyze feature attributions using SHAP, and assess the reliability of LLM-generated self-explanations. While LLMs are able to identify key financial risk indicators, their feature importance rankings diverge notably from LightGBM, and their self-explanations often fail to align with empirical SHAP attributions. These findings highlight the limitations of LLMs as standalone models for structured financial risk prediction and raise concerns about the trustworthiness of their self-generated explanations. Our results underscore the need for explainability audits, baseline comparisons with interpretable models, and human-in-the-loop oversight when deploying LLMs in risk-sensitive financial environments.

Residual Speech Embeddings for Tone Classification: Removing Linguistic Content to Enhance Paralinguistic Analysis

Self-supervised learning models for speech processing, such as wav2vec2, HuBERT, WavLM, and Whisper, generate embeddings that capture both linguistic and paralinguistic information, making it challenging to analyze tone independently of spoken content. In this work, we introduce a method for disentangling paralinguistic features from linguistic content by regressing speech embeddings onto their corresponding text embeddings and using the residuals as a representation of vocal tone. We evaluate this approach across multiple self-supervised speech embeddings, demonstrating that residual embeddings significantly improve tone classification performance compared to raw speech embeddings. Our results show that this method enhances linear separability, enabling improved classification even with simple models such as logistic regression. Visualization of the residual embeddings further confirms the successful removal of linguistic information while preserving tone-related features. These findings highlight the potential of residual embeddings for applications in sentiment analysis, speaker characterization, and paralinguistic speech processing.